philtabor / Actor-Critic-Methods-Paper-To-Code

philtabor/Actor-Critic-Methods-Paper-To-Code Issues

NaN Issue with SAC Code
Updated a year ago
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [256, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead.
Updated 2 years ago
Saving the networks, optimizers and replay buffer for resuming training.
Updated 3 years ago1
PPO algorithom?
Closed 4 years ago2
actor loss confusion
Closed 4 years ago1
why do you add the state_space and action_space?
Closed 4 years ago3